INDEX

Explanations

references to historical figures and organizations, particularly in the context of governance and architecture

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erdem

-0.14

 ilma

-0.14

 Millennials

-0.13

 WordPress

-0.12

 Huffington

-0.12

 bloggers

-0.12

FAQ

-0.12

 Wiki

-0.12

 Wikip

-0.12

 geek

-0.12

POSITIVE LOGITS

 miscellaneous

0.25

 Miscellaneous

0.25

 Folder

0.22

 folder

0.21

 copy

0.21

 Papers

0.21

 unidentified

0.21

 Correspond

0.21

 correspondence

0.21

 misc

0.21

Activations Density 0.317%

references to historical figures and organizations, particularly in the context of governance and architecture

No Comments

No Known Activations